Cshearer210

Cshearer210/claimproof

Agents claim work is done that isn't. This makes them prove it: evidence-gated turns, self-testing gates, live-state checks, and a ledger that catches "all done" lies. One-command Claude Code integration.

1 stars 2 forks 1 watchers Python MIT License
agents ai-agents claude-code evals guardrails llm python quality-assurance reliability testing
View on GitHub
1 Open Issue Need Help Last updated: Aug 8, 2026

Open Issues Need Help

View All on GitHub
Good first contribution: a stop-event adapter for another agent runtime (walkthrough included) about 2 hours ago
help wanted good first issue
Cshearer210/claimproof
1

Agents claim work is done that isn't. This makes them prove it: evidence-gated turns, self-testing gates, live-state checks, and a ledger that catches "all done" lies. One-command Claude Code integration.

Python
#agents#ai-agents#claude-code#evals#guardrails#llm#python#quality-assurance#reliability#testing